Qwen3.7 MaxvsKimi K2.6
Across 10 shared benchmarks, Qwen3.7 Max leads overall: Qwen3.7 Max wins 9, Kimi K2.6 wins 1, with 0 ties and an average score difference of +2.33.
Qwen3.7 Max
阿里巴巴 · 2026-05-20 · Reasoning model
Kimi K2.6
Moonshot AI · 2026-04-20 · Reasoning model
Qwen3.7 Max9 wins(90%)(10%)1 winKimi K2.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 10 shared benchmarks.
Coding and Software Engineer
Qwen3.7 Max 4/4| Benchmark | Qwen3.7 Max | Kimi K2.6 | Diff |
|---|---|---|---|
| LiveCodeBench | 91.604 / 126最高（无工具） | 89.608 / 126Thinking (No Tools) | +2 |
| SWE-Bench Pro - Public | 60.6012 / 57Thinking (With Tools) | 58.6015 / 57Thinking (With Tools) | +2 |
| SWE-bench Multilingual | 78.304 / 25Thinking (With Tools) | 76.705 / 25Thinking (With Tools) | +1.60 |
| SWE-bench Verified | 80.4013 / 114Thinking (With Tools) | 80.2014 / 114Thinking (With Tools) | +0.20 |
AI Agent - Tool Usage
Qwen3.7 Max 2/2| Benchmark | Qwen3.7 Max | Kimi K2.6 | Diff |
|---|---|---|---|
| MCP-Atlas | 76.4016 / 38Thinking (With Tools) | 69.4028 / 38Thinking (With Tools) | +7 |
| Terminal Bench 2.0 | 69.705 / 48Thinking (With Tools) | 66.7010 / 48Thinking (With Tools) | +3 |
General Knowledge
Even 2/2| Benchmark | Qwen3.7 Max | Kimi K2.6 | Diff |
|---|---|---|---|
| LiveBench | 74.2921 / 115Deep Thinking (No Tools) | 72.1728 / 115Thinking (No Tools) | +2.12 |
| HLE | 53.5018 / 181Thinking (With Tools) | 5417 / 181Thinking (With Tools + Internet) | -0.50 |
General Evaluation
Qwen3.7 Max 1/1| Benchmark | Qwen3.7 Max | Kimi K2.6 | Diff |
|---|---|---|---|
| GPQA Diamond | 92.4022 / 226最高（无工具） | 90.5035 / 226Thinking (No Tools) | +1.90 |
Math and Reasoning
Qwen3.7 Max 1/1| Benchmark | Qwen3.7 Max | Kimi K2.6 | Diff |
|---|---|---|---|
| IMO-AnswerBench | 903 / 23最高（无工具） | 8610 / 23Thinking (No Tools) | +4 |
Specs
| Field | Qwen3.7 Max | Kimi K2.6 |
|---|---|---|
| Publisher | 阿里巴巴 | Moonshot AI |
| Release date | 2026-05-20 | 2026-04-20 |
| Model type | Reasoning model | Reasoning model |
| Architecture | Dense | MoE |
| Parameters | Not available | 1T |
| Context length | 1M | 256K |
| Max output | 64K | Not available |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Qwen3.7 Max | Kimi K2.6 |
|---|---|---|
| Text input | ¥12 / 1M tokens | $0.95 / 1M tokens |
| Text output | ¥36 / 1M tokens | $4 / 1M tokens |
| Cache read | Not public | $0.16 / 1M tokens |
| Cache write | Not public | $0.95 / 1M tokens |
Summary
- Qwen3.7 Maxleads in:Coding and Software Engineer (4/4), AI Agent - Tool Usage (2/2), General Evaluation (1/1), Math and Reasoning (1/1)
- Tied in:General Knowledge
On average across the 10 shared benchmarks, Qwen3.7 Max scores 2.33 higher.
Largest single-benchmark gap: MCP-Atlas — Qwen3.7 Max 76.40 vs Kimi K2.6 69.40 (+7).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.